CN107086935A - Flow of the people distribution forecasting method based on WIFI AP - Google Patents
Flow of the people distribution forecasting method based on WIFI AP Download PDFInfo
- Publication number
- CN107086935A CN107086935A CN201710457666.3A CN201710457666A CN107086935A CN 107086935 A CN107086935 A CN 107086935A CN 201710457666 A CN201710457666 A CN 201710457666A CN 107086935 A CN107086935 A CN 107086935A
- Authority
- CN
- China
- Prior art keywords
- wifi
- equations
- data
- moment
- equipment
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/142—Network analysis or design using statistical or mathematical methods
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/145—Network analysis or design involving simulating, designing, planning or modelling of a network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/147—Network analysis or design for predicting network behaviour
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/08—Testing, supervising or monitoring using real traffic
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- Algebra (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Mathematical Physics (AREA)
- Probability & Statistics with Applications (AREA)
- Pure & Applied Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention relates to the airport Trip distribution Forecasting Methodology recorded based on WIFI AP, it is related to big data and excavates processing technology field, WIFI AP records, which are obtained, from control centre carries out pretreatment operation, pass through WIFI AP access device quantitative classification WIFI AP, training sample set is built respectively for all kinds of WIFI AP, regression model is built respectively using respective training sample set, test sample collection is obtained according to regression model, the test sample collection for gathering the first class model and the second class model is predicted the outcome, and predicts airport Trip distribution.The present invention utilizes correlation properties, and using the correlation technique of data mining and machine learning, the Trip distribution on airport is predicted, and reaches and effectively utilizes Airport Resources.
Description
Technical field
The present invention relates to technical field of computer information processing, and in particular to data mining and machine learning association area.
Background technology
Play all the more important effect in life as the data mining of raw material and machine learning techniques using data, pass through
" knowledge " in mining data, reaches the purpose using data.Airport at every moment produces data, in departure hall, nothing
Line WIFI covers whole region, and WIFI access access point AP (access point) record the passenger connection people at per moment
Number, is recorded by WIFI AP, passenger's spatial and temporal distributions at estimation current time that can be substantially.The spatial and temporal distributions and aircraft of passenger
Landing it is also very related, a period of time after aircraft is reached, or a period of time before taking off, portion passenger
Density can increase, and this is also the crucial foundation for estimating passenger's spatial and temporal distributions.How such data are effectively utilized, rationally application
It is a key issue for how improving airport efficiency of service in following passenger's spatial and temporal distributions of prediction.
Meanwhile, the present invention is not limited only to prediction of the airport to flow of the people, is readily applicable to other shopping mall places
Deng the big place of flow of the people, AP quantity is accessed by WIFI, judgement is predicted to flow of the people, during convenient generation emergency
Evacuate etc..The method that prior art is used can only observe the flow space-time distribution at current time, it is impossible to realize to future
Certain section of time Trip distribution is predicted.
The content of the invention
The present invention for above-mentioned technical problem present in prior art there is provided one kind based on airport WIFI AP records and
Flight is arranged an order according to class and grade the airport Trip distribution forecasting system of record, it is intended to solve the problems, such as airport traffic forecast of distribution.Can be according to pre-
Passenger's spatial and temporal distributions of survey, carry out advance plan and arrangement, reach and more effectively utilize Airport Resources, more preferable airport clothes
Business.
The technical scheme that the present invention solves above-mentioned technical problem is to provide one kind based on WIFI AP (wireless device access numbers
Amount) record airport Trip distribution Forecasting Methodology, including：WIFI AP records are obtained from control centre and carry out pretreatment operation, are led to
WIFI AP access device quantitative classification WIFI AP are crossed, is that all kinds of WIFI AP build training sample set respectively, uses training sample
Collection builds regression model；Build test sample collection and predict airport Trip distribution.
Carry out pretreatment operation to specifically include, missing values processing is carried out to the WIFI AP records of acquisition, for a certain WIFI
AP missing data, quantity is connected using with the equipment at the record corresponding moment WIFI AP in the nearest predetermined number of days D of missing data
Average be filled；The data after filling are smoothly located using arma modeling (autoregressive moving-average model)
Reason, then carries out dirty data processing, to carrying out the WIFI AP data after dirty data processing, according to formula：Calculating should
I-th of period after WIFI AP stipulations equipment connection quantity, in units of predetermined amount of time T to WIFI AP connection numbers with
Average value carries out stipulations, wherein, xijEquipment for the jth moment of i-th of period of the WIFI AP connects quantity.
The classification WIFI AP are specifically included, for each WIFI AP, calculate the variance that its equipment connects number, and according to
Its variance is descending to be ranked up, and WIFI AP then are divided into two classes, the less WIFI AP of variance using sixteen rules
For first kind WIFI AP, the larger WIFI AP of variance are Equations of The Second Kind WIFI AP.
For first kind WIFI AP, nearest predetermined number of days D data are taken, first kind WIFI AP training sets are set up.
For Equations of The Second Kind WIFI AP, nearest predetermined number of days D data are taken, the is built by tag extraction and feature extraction
Two class training sets.Label, with being characterized in two parts for constituting sample, is characterized in the performance of each attribute of sample, label is to sample
This has the attribute of marking behavior.By feature and label, a sample is constituted.
Build Equations of The Second Kind training set method be：The WIFI AP that numbering is i are taken in the equipment connection quantity y at j moment, structure
Into sample x (i, j, F, y), wherein, F be the sample feature, include 3 part subcharacters：(1) history feature：For the WIFI
AP synchronization, calculates the WIFI AP in the average of the synchronization in units of day, minimum value, maximum and side respectively
Poor information.(2) flight feature：Arranged an order according to class and grade according to flight the boarding gate positional information of record, count the boarding gate position-scheduled period
Interior (in 10 minutes, 30 minutes, 60 minutes and 120 minutes) take off quantity, and associate with WIFI AP positional information laggard
Row data merge.(3) position feature is obtained：Include the region where WIFI AP, place floor, place group # and WIFI AP
Coordinate information.
For first kind WIFI AP, using first kind WIFI AP training sets, according to formulaCalculate numbering i
WIFI AP the j moment predicted value yij, build first kind WIFI AP regression modelsWherein, xijkFor numbering i
The WIFI AP kth day j moment equipment connection quantity, set1 be the first kind WIFI AP set.According to the first class model Y1Enter
Row prediction, draws first kind WIFI AP equipment connection quantity.
For Equations of The Second Kind WIFI AP, its feature is that the variance of equipment connection number is higher.For this kind of WIFI AP, according to pre-
The data for surveying D of nearest predetermined number of days a few days ago carry out tag extraction, carry out feature extraction and obtain Equations of The Second Kind training sample set, formula yij
=h (xij) calculate numbering i WIFI AP the j moment predicted value yIj,Build Equations of The Second Kind regression modelWherein,
xijFor forecast sample, the acquisition methods of forecast sample are identical with the method for Equations of The Second Kind training set sample, the label of the juxtaposition sample
For sky, set2 gathers for Equations of The Second Kind WIFI AP, and h functions are divided for what is trained using Equations of The Second Kind training set based on optimal leaf
GBDT regression models.Use the second class model Y2It is predicted, draws Equations of The Second Kind WIFI AP equipment connection quantity.
According to formula Y=Y1∪Y2First class model and the second class model are carried out integrated.To the prediction knot of the first class model
Predicting the outcome for fruit and the second class model is integrated, as finally predicting the outcome.Predict the outcome is each WIFI AP in predicted time
The equipment access number at interior each moment, accesses number by each WIFI AP equipment, obtains each WIFI AP location
People's fluxion in domain, the information such as density of stream of people.
The method connects the spy for the long tail effect having after the variance sequence of quantity by each WIFI AP equipment
WIFI AP points, are divided into two classes by point using sixteen principles, and this two classes WIFI AP is modeled respectively, relative to foundation in single mode
In the method for type prediction, the method predicts the outcome more accurate.
Brief description of the drawings
In order to illustrate more clearly of the technical scheme in the embodiment of the present application, make required in being described below to embodiment
Accompanying drawing is briefly described.
A kind of airport Trip distribution Forecasting Methodology flow chart recorded based on airport WIFI AP that Fig. 1 provides for the present invention.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present application, the technical scheme to the application carries out clear, complete description,
Obviously, described embodiment is only some embodiments of the present application, rather than whole embodiments, it is impossible to limit this accordingly
The technical scheme of invention, and rights protection scope.Those of ordinary skill in the art may obtain in no process creative work
Every other embodiment, belong to the application protection scope.
A kind of airport Trip distribution for record of being arranged an order according to class and grade based on airport WIFI AP records and flight that Fig. 1 provides for the present invention
The flow chart of Forecasting Methodology, is specifically included：
WIFI AP record is obtained from control centre and flight is arranged an order according to class and grade record, and general WIFI AP records are arranged comprising three, first
WIFI AP label is classified as, record of arranging an order according to class and grade includes four row, is respectively：Flight number etc..Choose nearest predetermined number of days D (such as 30 days)
Record.Wherein, WIFI AP records include three row, and first is classified as WIFI AP label, includes WIFI AP intrinsic information,
Region, place floor, place group # and WIFI AP coordinate informations predominantly where WIFI AP, second is classified as WIFI AP
Equipment connection quantity, the 3rd is classified as timestamp.Flight, which arranges an order according to class and grade to record, includes four row, is respectively：Flight number, during predetermined landing
Between, actual landing time and boarding gate information.
The WIFI AP of acquisition are recorded and flight is arranged an order according to class and grade to record and carries out missing values processing.For a certain WIFI AP missing
Data, it is corresponding using the average that quantity is connected with the corresponding moment equipment that the missing data nearest predetermined number of days WIFI AP records
Correlation values be filled.
Dirty data processing is carried out to the WIFI AP records after missing values are handled.Data are carried out using arma modeling
Smoothing processing.For each WIFI AP, quantity is accessed by inputting the WIFI AP equipment of its continuous time, output is passed through
The WIFI AP of continuous time after arma modeling processing equipment access quantity, the characteristics of output data is compared with input data be, respectively
The equipment access quantity of WIFI AP points changes with time more smooth.To entering the WIFI AP data after dirty data processing
Carry out hough transformation.It is that unit carries out stipulations to WIFI AP connection numbers with average value with predetermined amount of time T (such as 10 minutes), i.e.,
A data is generated per period T.According to formulaCalculate i-th of predetermined amount of time after the WIFI AP stipulations
Equipment connection quantity ri, wherein, xijEquipment for the jth minute of certain i-th of predetermined amount of time of WIFI AP connects quantity.
For each WIFI AP, calculate its equipment and connect the variance of number, and be ranked up according to its variance is descending,
Then it is two classes to divide WIFI AP using sixteen rules.The less WIFI AP of variance are first kind WIFI AP, and variance is larger
WIFI AP are Equations of The Second Kind WIFI AP.The computational methods of variance are：Equipment of a certain WIFI AP in each time is taken to access quantity
The sequence constituted, calculates the variance of the sequence, is used as the variance of the WIFI AP.Sixteen rule division methods are：Take preceding 20%
The larger WIFI AP of variance as Equations of The Second Kind WIFI AP, the less WIFI AP of variance for taking rear 80% are first kind WIFI
AP。
For first kind WIFI AP, nearest predetermined number of days D data are taken, first kind WIFI AP training sets are set up, trained
Collection is made up of some sample x (i, j, y), wherein, i is WIFI AP numbering, and j is a certain moment, and y is numbering i WIFI AP
Quantity is connected in the equipment at j moment.
For Equations of The Second Kind WIFI AP, tag extraction is carried out using the data for predicting D of nearest predetermined number of days a few days ago, label is
The WIFI AP of a certain moment equipment connection number, feature extraction is carried out to Equations of The Second Kind WIFI AP.According to above-mentioned fetched data
Feature extraction is carried out, wherein packet AP containing the WIFI records and flight record that obtain.
Its feature includes 3 parts：
(1) history feature：For the synchronization of the WIFI AP, the WIFI AP are calculated respectively same in units of day
Average, minimum value, maximum and the covariance information at one moment.
(2) flight feature：Flight is one of principal element of influence connection number fluctuation, is believed according to the boarding gate position of flight
Breath, count the boarding gate position at interval of predetermined amount of time flight takeoff land quantity, and with WIFI AP positional information
Data merging is carried out after association, flight feature is obtained.
(3) position feature：Include the region where WIFI AP, place floor, place group # and WIFI AP coordinates letter
Breath.
For first kind WIFI AP, according to first kind WIFI AP training sets, according to formulaCalculate numbering i
WIFI AP the j moment equipment connection number yij, build first kind WIFI AP regression modelsWherein, xijkFor
The equipment connection quantity at numbering i WIFI AP kth day j moment, set1 gathers for first kind WIFI AP.According to the first class model
Y1It is predicted, predicts the outcome as P1.Predict the outcome P1For prediction certain WIFI AP certain moment equipment connect quantity.
For Equations of The Second Kind WIFI AP, its feature is that the variance of equipment connection number is higher.For this kind of WIFI AP, according to public affairs
Formula yij=h (xij) calculate numbering i WIFI AP the j moment predicted value yIj,Build Equations of The Second Kind regression modelIts
In, xijFor test sample, set2 is Equations of The Second Kind WIFI AP set, h functions for using Equations of The Second Kind training set trained based on most
Excellent leaf divides GBDT regression models.Use the second class model Y2It is predicted, predicts the outcome as P2。P2It is according to Equations of The Second Kind
The equipment connection quantity for certain WIFI AP that WIFI AP training sets are obtained.
Training set is the training sample set that Equations of The Second Kind training set, i.e. Equations of The Second Kind WIFI AP are constituted, and training method is defeated
Enter training set, forecast model built by GBDT algorithms, rear input prediction collection is predicted by the GBDT models built,
One sample (record) is made up of feature and label, and one group of feature one label of correspondence, label connects for the equipment of the WIFI AP
Quantity.
According to formula Y=Y1∪Y2First class model and the second class model are carried out integrated.
According to formula P=P1∪P2To the first class model predict the outcome and the second class model predict the outcome it is integrated, as
Finally predict the outcome.The equipment for each WIFI AP at each moment that predicts the outcome accesses number.
Claims (5)
1. the flow of the people distribution forecasting method recorded based on WIFI AP, it is characterised in that：Including step：Obtained from control centre
WIFI AP records carry out pretreatment operation, and it is two classes to be divided to WIFI AP by WIFI AP access devices quantity, is all kinds of WIFI
AP builds training sample set respectively, and corresponding regression model is built respectively using respective training sample set, calls respective time
Model is returned to obtain test sample collection, the test sample collection for gathering all kinds of regression models is predicted the outcome, prediction airport passenger flow point
Cloth.
2. according to the method described in claim 1, it is characterised in that carry out pretreatment operation and specifically include, to the WIFI of acquisition
AP records carry out missing values processing, for a certain WIFI AP missing data, using with the nearest predetermined number of days D of missing data
The average of the equipment connection quantity at the record correspondence moment WIFI AP is filled；Data are carried out using arma modeling smooth
Processing；Dirty data processing is carried out to WIFI AP records, to carrying out the WIFI AP data after dirty data processing, according to formula：The equipment connection quantity of i-th of period after the WIFI AP stipulations is calculated, it is right in units of predetermined amount of time T
WIFI AP connection numbers carry out stipulations with average value, wherein, xijEquipment for the jth moment of i-th of period of the WIFI AP connects
Connect quantity.
3. according to the method described in claim 1, it is characterised in that the classification WIFI AP are specifically included, for each WIFI
AP, calculates the variance that its equipment connects number, and is ranked up according to its variance is descending, then using sixteen rules by WIFI
AP is divided into two classes, and the less WIFI AP of variance are first kind WIFI AP, and the larger WIFI AP of variance are Equations of The Second Kind WIFI
AP。
4. method according to claim 3, it is characterised in that for first kind WIFI AP, connected with WIFI AP equipment
Quantity is connect as WIFI AP training sets, according to WIFI AP training sets, formula is calledCalculate numbering i WIFI
Predicted value ys of the AP at the j momentij, build first kind WIFI AP regression modelsWherein, xijkFor numbering i WIFI
The equipment connection quantity at AP kth day j moment, set1 gathers for first kind WIFI AP.
5. method according to claim 3, it is characterised in that a few days ago pre- recently according to prediction for Equations of The Second Kind WIFI AP
The data for determining number of days D carry out tag extraction, extract feature and obtain training sample set, according to formula yij=h (xij) calculate numbering i
WIFI AP the j moment predicted value yIj,Build Equations of The Second Kind regression modelWherein, xijFor test sample, set2
For Equations of The Second Kind WIFI AP gather, h functions for using the Equations of The Second Kind training set constructed by S1032 trained based on optimal leaf
The GBDT regression models of division.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710457666.3A CN107086935B (en) | 2017-06-16 | 2017-06-16 | People flow distribution prediction method based on WIFI AP |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710457666.3A CN107086935B (en) | 2017-06-16 | 2017-06-16 | People flow distribution prediction method based on WIFI AP |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107086935A true CN107086935A (en) | 2017-08-22 |
| CN107086935B CN107086935B (en) | 2020-05-12 |
Family
ID=59606305
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710457666.3A Active CN107086935B (en) | 2017-06-16 | 2017-06-16 | People flow distribution prediction method based on WIFI AP |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107086935B (en) |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107657335A (en) * | 2017-09-06 | 2018-02-02 | 武汉科技大学 | A kind of spatial and temporal distributions Forecasting Methodology of airport traffic |
| CN107679647A (en) * | 2017-09-06 | 2018-02-09 | 武汉科技大学 | A kind of spatial and temporal distributions prediction meanss of airport traffic |
| CN108038116A (en) * | 2017-10-24 | 2018-05-15 | 安徽四创电子股份有限公司 | A kind of density of stream of people monitoring method based on GIS |
| CN108260087A (en) * | 2018-01-31 | 2018-07-06 | 福州大学 | A kind of indoor stream of people's distribution forecasting method based on WIIFI long short-term memories |
| CN108306962A (en) * | 2018-01-30 | 2018-07-20 | 河海大学常州校区 | A kind of business big data analysis system |
| CN108376292A (en) * | 2017-12-12 | 2018-08-07 | 广州汇智通信技术有限公司 | A kind of crowd's method for predicting, system and equipment |
| CN109120463A (en) * | 2018-10-15 | 2019-01-01 | 新华三大数据技术有限公司 | Method for predicting and device |
| CN109214612A (en) * | 2018-11-20 | 2019-01-15 | 广东机场白云信息科技有限公司 | One kind being based on XGBOOST airport traffic spatial and temporal distributions prediction technique |
| CN109362034A (en) * | 2018-11-22 | 2019-02-19 | 南京茶非氪信息科技有限公司 | A kind of macro-regions communication channel temperature prediction technique |
| CN109492788A (en) * | 2017-09-13 | 2019-03-19 | 中移（杭州）信息技术有限公司 | Prediction flow of the people and the method and relevant device for establishing flow of the people prediction model |
| CN109657700A (en) * | 2018-11-22 | 2019-04-19 | 南京茶非氪信息科技有限公司 | A kind of macro-regions communication channel temperature detection algorithm |
| CN110060102A (en) * | 2019-04-18 | 2019-07-26 | 重庆邮电大学 | Retail shop where user based on inclined label study positions big data prediction technique |
| CN110166945A (en) * | 2019-06-04 | 2019-08-23 | 中国民用航空总局第二研究所 | Terminal passenger traffic volume dynamic prediction method, device, medium and equipment |
| CN111209180A (en) * | 2018-11-21 | 2020-05-29 | 中国移动通信集团浙江有限公司 | Regression testing method and device based on fuzzy matching |
| TWI716061B (en) * | 2019-08-02 | 2021-01-11 | 中華電信股份有限公司 | Fault prediction device and fault prediction method for base station |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8532069B2 (en) * | 2005-09-23 | 2013-09-10 | Ramesh Balwani | Local area wireless airspace management |
| CN104573859A (en) * | 2014-12-31 | 2015-04-29 | 合肥城市云数据中心有限公司 | Human traffic prediction method based on Wifi positioning and cloud data processing technology |
| CN205283824U (en) * | 2015-11-24 | 2016-06-01 | 如东信息技术服务(上海)有限公司 | Airport stream of people early warning system based on wifi |
| CN106407706A (en) * | 2016-09-29 | 2017-02-15 | 北京理工大学 | Boruta algorithm-based multi-level old people physical state quantization level calculation method |
-
2017
- 2017-06-16 CN CN201710457666.3A patent/CN107086935B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8532069B2 (en) * | 2005-09-23 | 2013-09-10 | Ramesh Balwani | Local area wireless airspace management |
| CN104573859A (en) * | 2014-12-31 | 2015-04-29 | 合肥城市云数据中心有限公司 | Human traffic prediction method based on Wifi positioning and cloud data processing technology |
| CN205283824U (en) * | 2015-11-24 | 2016-06-01 | 如东信息技术服务(上海)有限公司 | Airport stream of people early warning system based on wifi |
| CN106407706A (en) * | 2016-09-29 | 2017-02-15 | 北京理工大学 | Boruta algorithm-based multi-level old people physical state quantization level calculation method |
Non-Patent Citations (3)
| Title |
|---|
| HTTPS://BLOG.CSDN.NET/ERIC2016_LV/ARTICLE/DETAILS/53483716: "机器学习小组知识点24：数据预处理之数据清理（Data-Cleaning）", 《CSDN博客》 * |
| HTTPS://BLOG.CSDN.NET/ERIC2016_LV/ARTICLE/DETAILS/53487700: "机器学习小组知识点26：数据预处理之数据规约（Data Reduction）", 《CSDN博客》 * |
| HTTPS://BLOG.CSDN.NET/U014135091/ARTICLE/DETAILS/53396336: "数据竞赛思路分享：机场客流量的时空分布预测", 《CSDN博客》 * |
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107679647A (en) * | 2017-09-06 | 2018-02-09 | 武汉科技大学 | A kind of spatial and temporal distributions prediction meanss of airport traffic |
| CN107679647B (en) * | 2017-09-06 | 2019-12-24 | 武汉科技大学 | Spatial-temporal distribution prediction device for airport passenger flow |
| CN107657335A (en) * | 2017-09-06 | 2018-02-02 | 武汉科技大学 | A kind of spatial and temporal distributions Forecasting Methodology of airport traffic |
| CN109492788A (en) * | 2017-09-13 | 2019-03-19 | 中移（杭州）信息技术有限公司 | Prediction flow of the people and the method and relevant device for establishing flow of the people prediction model |
| CN109492788B (en) * | 2017-09-13 | 2020-12-11 | 中移（杭州）信息技术有限公司 | Method for predicting pedestrian flow and establishing pedestrian flow prediction model and related equipment |
| CN108038116A (en) * | 2017-10-24 | 2018-05-15 | 安徽四创电子股份有限公司 | A kind of density of stream of people monitoring method based on GIS |
| CN108376292A (en) * | 2017-12-12 | 2018-08-07 | 广州汇智通信技术有限公司 | A kind of crowd's method for predicting, system and equipment |
| CN108306962A (en) * | 2018-01-30 | 2018-07-20 | 河海大学常州校区 | A kind of business big data analysis system |
| CN108306962B (en) * | 2018-01-30 | 2021-09-28 | 河海大学常州校区 | Commercial big data analysis system |
| CN108260087A (en) * | 2018-01-31 | 2018-07-06 | 福州大学 | A kind of indoor stream of people's distribution forecasting method based on WIIFI long short-term memories |
| CN109120463B (en) * | 2018-10-15 | 2022-01-07 | 新华三大数据技术有限公司 | Flow prediction method and device |
| CN109120463A (en) * | 2018-10-15 | 2019-01-01 | 新华三大数据技术有限公司 | Method for predicting and device |
| CN109214612A (en) * | 2018-11-20 | 2019-01-15 | 广东机场白云信息科技有限公司 | One kind being based on XGBOOST airport traffic spatial and temporal distributions prediction technique |
| CN111209180B (en) * | 2018-11-21 | 2023-04-25 | 中国移动通信集团浙江有限公司 | Regression testing method and device based on fuzzy matching |
| CN111209180A (en) * | 2018-11-21 | 2020-05-29 | 中国移动通信集团浙江有限公司 | Regression testing method and device based on fuzzy matching |
| CN109657700A (en) * | 2018-11-22 | 2019-04-19 | 南京茶非氪信息科技有限公司 | A kind of macro-regions communication channel temperature detection algorithm |
| CN109657700B (en) * | 2018-11-22 | 2022-11-11 | 南京茶非氪信息科技有限公司 | Macroscopic region communicating channel heat degree detection method |
| CN109362034A (en) * | 2018-11-22 | 2019-02-19 | 南京茶非氪信息科技有限公司 | A kind of macro-regions communication channel temperature prediction technique |
| CN110060102A (en) * | 2019-04-18 | 2019-07-26 | 重庆邮电大学 | Retail shop where user based on inclined label study positions big data prediction technique |
| CN110060102B (en) * | 2019-04-18 | 2022-05-03 | 重庆邮电大学 | Bias label learning-based method for predicting positioning big data of shops where users are located |
| CN110166945B (en) * | 2019-06-04 | 2020-11-24 | 中国民用航空总局第二研究所 | Method, device, medium and equipment for dynamically predicting passenger flow of terminal building |
| CN110166945A (en) * | 2019-06-04 | 2019-08-23 | 中国民用航空总局第二研究所 | Terminal passenger traffic volume dynamic prediction method, device, medium and equipment |
| TWI716061B (en) * | 2019-08-02 | 2021-01-11 | 中華電信股份有限公司 | Fault prediction device and fault prediction method for base station |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107086935B (en) | 2020-05-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107086935A (en) | Flow of the people distribution forecasting method based on WIFI AP | |
| CN110364008A (en) | Road conditions determine method, apparatus, computer equipment and storage medium | |
| CN105279572B (en) | City track traffic passenger flow density index calculating and releasing system | |
| Notomista et al. | A fast airplane boarding strategy using online seat assignment based on passenger classification | |
| CN107229708A (en) | A kind of personalized trip service big data application system and method | |
| CN102521965B (en) | Effect evaluation method of traffic demand management measures based on identification data of license plates | |
| CN106778876A (en) | User classification method and system based on mobile subscriber track similitude | |
| CN107609708A (en) | A kind of customer loss Forecasting Methodology and system based on mobile phone games shop | |
| CN102663164B (en) | Pass control algorithm test device and method based on multiobjective test case generation | |
| CN106971634A (en) | A kind of spatial domain collision detection method predicted based on aircraft's flight track and system | |
| CN107481511A (en) | A kind of method and system for calculating candidate bus station | |
| CN108629000A (en) | A kind of the group behavior feature extracting method and system of mobile phone track data cluster | |
| CN107742168A (en) | A kind of workshop bottleneck Forecasting Methodology based on Internet of Things technology | |
| CN107392389A (en) | Taxi dispatching processing method based on ARIMA models | |
| CN109684373A (en) | Emphasis party based on trip and call bill data analysis has found method | |
| CN106447387A (en) | Air ticket personalized recommendation method based on shared account passenger prediction | |
| CN108091132A (en) | A kind of traffic flow forecasting method and device | |
| CN107978153A (en) | A kind of multimode traffic factors influencing demand analysis method based on space vector autoregression model | |
| CN103824450B (en) | Based on the large-scale activity Special running layout of roads method of traffic behavior rule | |
| CN102663491B (en) | Method for counting high density population based on SURF characteristic | |
| CN114873395B (en) | Elevator analysis system and elevator analysis method | |
| CN106778851A (en) | Social networks forecasting system and its method based on Mobile Phone Forensics data | |
| CN106815563A (en) | A kind of crowd's quantitative forecasting technique based on human body apparent structure | |
| Cordera et al. | Trip distribution model for regional railway services considering spatial effects between stations | |
| CN106370198A (en) | Route selection method taking outgoing delayed reaction into account |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |